Cleaner model download instructions

Author: danielholanda

playbooks/core/lmstudio-rocm-llms/README.md

@@ -18,21 +18,13 @@ LM Studio is a powerful GUI-based wrapper for [llama.cpp](https://github.com/ggm
 <!-- @setup:memory-config -->
 
 
-## Downloading models
+## Downloading Models
 
-Your LM Studio instance in the STX Halo™ comes with OpenAI GPT-OSS 120B pre-downloaded.
-
-
-Should you wish to download additional models - you can do so by pressing "Ctrl" + "Shift" + "M" on your keyboard or clicking on the "Discover" tab (Magnifying Glass) and searching for additional models.
-
-LM Studio will automatically download and put the model in the correct directory.
+<!-- @require:lmstudio-models-gpt-oss-120b -->
 
 ## Chatting with an LLM
 Learn how to start chatting with a ChatGPT-grade LLM completely locally.  
 
-
-> This example uses OpenAI GPT-OSS 120B in its original MXFP4 precision. Please make sure to have completed the [System Setup](#system-setup) section above for optimal performance.
-
 1. Press "Ctrl" + "L" or select the central drop down menu at the top. Select "manually chose model load parameters" and click on "OpenAI GPT-OSS 120B"
 2. Make sure "show advanced settings" is checked.  
 3. Change context size to "128,000". Make sure "Flash Attention" is On and "GPU offload layers" is set to maximum.

playbooks/dependencies/assets/lmstudio_download.png

@@ -0,0 +1,14 @@
+### Downloading GPT-OSS 120B on LM Studio
+
+To download the GPT-OSS 120B model:
+
+1. Press "Ctrl" + "Shift" + "M" on your keyboard or click on the "Discover" tab (Magnifying Glass icon) on the left sidebar
+2. Search for `ggml-org/gpt-oss-120b-GGUF`
+3. Select `mxfp4` and click Download
+
+<p align="center">
+  <img src="/api/dependencies/assets/lmstudio_download.png" alt="LM Studio Download Models" width="600"/>
+
+LM Studio will automatically download and place the model in the correct directory.
+
+Should you wish to download additional models, you can search for them in the Discover tab and LM Studio will handle the rest.

playbooks/dependencies/lmstudio_models_gpt_oss_120b.md

@@ -51,6 +51,13 @@
       "platforms": ["windows", "linux"],
       "file": "comfyui_models.md"
     },
+    "lmstudio-models-gpt-oss-120b": {
+      "name": "GPT-OSS 120B Model",
+      "description": "OpenAI GPT-OSS 120B model for LM Studio",
+      "category": "model",
+      "platforms": ["windows", "linux"],
+      "file": "lmstudio_models_gpt_oss_120b.md"
+    },
     "driver": {
       "name": "AMD GPU Driver",
       "description": "Latest AMD GPU driver for optimal performance",